skills/tigrisdata/skills/file-storage/Gen Agent Trust Hub

file-storage

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill provides technical documentation and code snippets for using Tigris Object Storage.
  • [DATA_EXFILTRATION]: The skill encourages secure practices by instructing users to store credentials in .env files and explicitly warns against exposing Secret Access Keys to client-side code.
  • [COMMAND_EXECUTION]: Shell commands are restricted to the official Tigris CLI (tigris or its alias t3) for legitimate tasks such as authentication, bucket creation, and access key management.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates reading file content through the SDK's get method. While this introduces a potential surface for indirect prompt injection from stored files, it is a primary function of the storage integration. Standard precautions should be taken when the agent processes data from external sources.
  • [EXTERNAL_DOWNLOADS]: Dependencies include official vendor packages (@tigrisdata/storage, @tigrisdata/react) which are standard for the described use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 10:20 PM